Back to Search Start Over

Modular Quantization-Aware Training: Increasing Accuracy by Decreasing Precision in 6D Object Pose Estimation

Authors :
Javed, Saqib
Li, Chengkun
Price, Andrew
Hu, Yinlin
Salzmann, Mathieu
Javed, Saqib
Li, Chengkun
Price, Andrew
Hu, Yinlin
Salzmann, Mathieu
Publication Year :
2023

Abstract

Edge applications, such as collaborative robotics and spacecraft rendezvous, demand efficient 6D object pose estimation on resource-constrained embedded platforms. Existing 6D pose estimation networks are often too large for such deployments, necessitating compression while maintaining reliable performance. To address this challenge, we introduce Modular Quantization-Aware Training (MQAT), an adaptive and mixed-precision quantization-aware training strategy that exploits the modular structure of modern 6D pose estimation architectures. MQAT guides a systematic gradated modular quantization sequence and determines module-specific bit precisions, leading to quantized models that outperform those produced by state-of-the-art uniform and mixed-precision quantization techniques. Our experiments showcase the generality of MQAT across datasets, architectures, and quantization algorithms. Remarkably, MQAT-trained quantized models achieve a significant accuracy boost (>7%) over the baseline full-precision network while reducing model size by a factor of 4x or more.

Details

Database :
OAIster
Publication Type :
Electronic Resource
Accession number :
edsoai.on1381608944
Document Type :
Electronic Resource